That framing resonates a lot. In production, creativity is often just unbounded variance.

Once each step is intentionally boring and constrained, failures become predictable and debuggable — which is what engineering actually optimizes for. That tradeoff is almost always worth it.

I’m building Verdic Guard (verdic.dev) around the same idea: treat LLMs as creative generators, but enforce scope and correctness outside the model so systems stay calm under load.